Towards Reliable Automatic Multimodal Content Analysis

Olli-Philippe Lautenbacher; Liisa Tiittula; Maija Hirvonen; Jorma Laaksonen; Mikko Kurimo

doi:10.18653/v1/w15-2803

Towards Reliable Automatic Multimodal Content Analysis

Olli-Philippe Lautenbacher, Liisa Tiittula, Maija Hirvonen, Jorma Laaksonen, Mikko Kurimo

Research output: Other conference contribution › Poster › Scientific

Abstract

This poster presents a pilot where audio description is used to enhance automatic content analysis, for a project aiming at creating a tool for easy access to large AV archives.

Original language	English
Pages	6-7
DOIs	https://doi.org/10.18653/v1/w15-2803
Publication status	Published - 2015
Externally published	Yes
Publication type	Not Eligible
Event	Workshop on Vision and Language - Lissabon, Portugal Duration: 18 Sep 2015 → …

Conference

Conference	Workshop on Vision and Language
Country/Territory	Portugal
City	Lissabon
Period	18/09/15 → …

Access to Document

10.18653/v1/w15-2803

Cite this

@conference{466f69c83ae349d093b074d90ba84a15,

title = "Towards Reliable Automatic Multimodal Content Analysis",

abstract = "This poster presents a pilot where audio description is used to enhance automatic content analysis, for a project aiming at creating a tool for easy access to large AV archives.",

author = "Olli-Philippe Lautenbacher and Liisa Tiittula and Maija Hirvonen and Jorma Laaksonen and Mikko Kurimo",

year = "2015",

doi = "10.18653/v1/w15-2803",

language = "English",

pages = "6--7",

note = "Workshop on Vision and Language ; Conference date: 18-09-2015",

}

TY - CONF

T1 - Towards Reliable Automatic Multimodal Content Analysis

AU - Lautenbacher, Olli-Philippe

AU - Tiittula, Liisa

AU - Hirvonen, Maija

AU - Laaksonen, Jorma

AU - Kurimo, Mikko

PY - 2015

Y1 - 2015

N2 - This poster presents a pilot where audio description is used to enhance automatic content analysis, for a project aiming at creating a tool for easy access to large AV archives.

AB - This poster presents a pilot where audio description is used to enhance automatic content analysis, for a project aiming at creating a tool for easy access to large AV archives.

U2 - 10.18653/v1/w15-2803

DO - 10.18653/v1/w15-2803

M3 - Poster

SP - 6

EP - 7

T2 - Workshop on Vision and Language

Y2 - 18 September 2015

ER -